-
Notifications
You must be signed in to change notification settings - Fork 12.9k
Closed
Labels
Description
This model: https://huggingface.co/nvidia/ChatQA-1.5-8B
Conversion worked no issue, but then when it's time to calculate the imatrix I see:
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 323, got 291
Doing a search, last time slaren mentioned doing a gguf-dump.py, here's the output:
* Loading: /models/ChatQA-1.5-8B-GGUF/ChatQA-1.5-8B-fp16.gguf
* File is LITTLE endian, script is running on a LITTLE endian host.
llama_cpp-1 |
* Dumping 24 key/value pair(s)
1: UINT32 | 1 | GGUF.version = 3
2: UINT64 | 1 | GGUF.tensor_count = 323
3: UINT64 | 1 | GGUF.kv_count = 21
4: STRING | 1 | general.architecture = 'llama'
5: STRING | 1 | general.name = 'ChatQA-1.5-8B'
6: UINT32 | 1 | llama.block_count = 32
7: UINT32 | 1 | llama.context_length = 8192
8: UINT32 | 1 | llama.embedding_length = 4096
9: UINT32 | 1 | llama.feed_forward_length = 14336
10: UINT32 | 1 | llama.attention.head_count = 32
11: UINT32 | 1 | llama.attention.head_count_kv = 8
12: FLOAT32 | 1 | llama.rope.freq_base = 500000.0
13: FLOAT32 | 1 | llama.attention.layer_norm_rms_epsilon = 9.999999747378752e-06
14: UINT32 | 1 | general.file_type = 1
15: UINT32 | 1 | llama.vocab_size = 128256
16: UINT32 | 1 | llama.rope.dimension_count = 128
17: STRING | 1 | tokenizer.ggml.model = 'gpt2'
18: STRING | 1 | tokenizer.ggml.pre = 'llama-bpe'
19: [STRING] | 128256 | tokenizer.ggml.tokens
20: [INT32] | 128256 | tokenizer.ggml.token_type
21: [STRING] | 280147 | tokenizer.ggml.merges
22: UINT32 | 1 | tokenizer.ggml.bos_token_id = 128000
23: UINT32 | 1 | tokenizer.ggml.eos_token_id = 128001
24: STRING | 1 | tokenizer.chat_template = '{% set loop_messages = messages %}{% for message in loop_mes'
llama_cpp-1 |
* Dumping 323 tensor(s)
1: 525336576 | 4096, 128256, 1, 1 | F16 | token_embd.weight
2: 4096 | 4096, 1, 1, 1 | F32 | blk.0.attn_norm.weight
3: 58720256 | 14336, 4096, 1, 1 | F16 | blk.0.ffn_down.weight
4: 58720256 | 4096, 14336, 1, 1 | F16 | blk.0.ffn_gate.weight
5: 58720256 | 4096, 14336, 1, 1 | F16 | blk.0.ffn_up.weight
6: 4096 | 4096, 1, 1, 1 | F32 | blk.0.ffn_norm.weight
7: 4194304 | 4096, 1024, 1, 1 | F16 | blk.0.attn_k.weight
8: 16777216 | 4096, 4096, 1, 1 | F16 | blk.0.attn_output.weight
9: 16777216 | 4096, 4096, 1, 1 | F16 | blk.0.attn_q.weight
10: 64 | 64, 1, 1, 1 | F32 | blk.0.attn_rot_embd
11: 4194304 | 4096, 1024, 1, 1 | F16 | blk.0.attn_v.weight
12: 4096 | 4096, 1, 1, 1 | F32 | blk.1.attn_norm.weight
13: 58720256 | 14336, 4096, 1, 1 | F16 | blk.1.ffn_down.weight
14: 58720256 | 4096, 14336, 1, 1 | F16 | blk.1.ffn_gate.weight
15: 58720256 | 4096, 14336, 1, 1 | F16 | blk.1.ffn_up.weight
16: 4096 | 4096, 1, 1, 1 | F32 | blk.1.ffn_norm.weight
17: 4194304 | 4096, 1024, 1, 1 | F16 | blk.1.attn_k.weight
18: 16777216 | 4096, 4096, 1, 1 | F16 | blk.1.attn_output.weight
19: 16777216 | 4096, 4096, 1, 1 | F16 | blk.1.attn_q.weight
20: 64 | 64, 1, 1, 1 | F32 | blk.1.attn_rot_embd
21: 4194304 | 4096, 1024, 1, 1 | F16 | blk.1.attn_v.weight
22: 4096 | 4096, 1, 1, 1 | F32 | blk.10.attn_norm.weight
23: 58720256 | 14336, 4096, 1, 1 | F16 | blk.10.ffn_down.weight
24: 58720256 | 4096, 14336, 1, 1 | F16 | blk.10.ffn_gate.weight
25: 58720256 | 4096, 14336, 1, 1 | F16 | blk.10.ffn_up.weight
26: 4096 | 4096, 1, 1, 1 | F32 | blk.10.ffn_norm.weight
27: 4194304 | 4096, 1024, 1, 1 | F16 | blk.10.attn_k.weight
28: 16777216 | 4096, 4096, 1, 1 | F16 | blk.10.attn_output.weight
29: 16777216 | 4096, 4096, 1, 1 | F16 | blk.10.attn_q.weight
30: 64 | 64, 1, 1, 1 | F32 | blk.10.attn_rot_embd
31: 4194304 | 4096, 1024, 1, 1 | F16 | blk.10.attn_v.weight
32: 4096 | 4096, 1, 1, 1 | F32 | blk.11.attn_norm.weight
33: 58720256 | 14336, 4096, 1, 1 | F16 | blk.11.ffn_down.weight
34: 58720256 | 4096, 14336, 1, 1 | F16 | blk.11.ffn_gate.weight
35: 58720256 | 4096, 14336, 1, 1 | F16 | blk.11.ffn_up.weight
36: 4096 | 4096, 1, 1, 1 | F32 | blk.11.ffn_norm.weight
37: 4194304 | 4096, 1024, 1, 1 | F16 | blk.11.attn_k.weight
38: 16777216 | 4096, 4096, 1, 1 | F16 | blk.11.attn_output.weight
39: 16777216 | 4096, 4096, 1, 1 | F16 | blk.11.attn_q.weight
40: 64 | 64, 1, 1, 1 | F32 | blk.11.attn_rot_embd
41: 4194304 | 4096, 1024, 1, 1 | F16 | blk.11.attn_v.weight
42: 4096 | 4096, 1, 1, 1 | F32 | blk.12.attn_norm.weight
43: 58720256 | 14336, 4096, 1, 1 | F16 | blk.12.ffn_down.weight
44: 58720256 | 4096, 14336, 1, 1 | F16 | blk.12.ffn_gate.weight
45: 58720256 | 4096, 14336, 1, 1 | F16 | blk.12.ffn_up.weight
46: 4096 | 4096, 1, 1, 1 | F32 | blk.12.ffn_norm.weight
47: 4194304 | 4096, 1024, 1, 1 | F16 | blk.12.attn_k.weight
48: 16777216 | 4096, 4096, 1, 1 | F16 | blk.12.attn_output.weight
49: 16777216 | 4096, 4096, 1, 1 | F16 | blk.12.attn_q.weight
50: 64 | 64, 1, 1, 1 | F32 | blk.12.attn_rot_embd
51: 4194304 | 4096, 1024, 1, 1 | F16 | blk.12.attn_v.weight
52: 4096 | 4096, 1, 1, 1 | F32 | blk.13.attn_norm.weight
53: 58720256 | 14336, 4096, 1, 1 | F16 | blk.13.ffn_down.weight
54: 58720256 | 4096, 14336, 1, 1 | F16 | blk.13.ffn_gate.weight
55: 58720256 | 4096, 14336, 1, 1 | F16 | blk.13.ffn_up.weight
56: 4096 | 4096, 1, 1, 1 | F32 | blk.13.ffn_norm.weight
57: 4194304 | 4096, 1024, 1, 1 | F16 | blk.13.attn_k.weight
58: 16777216 | 4096, 4096, 1, 1 | F16 | blk.13.attn_output.weight
59: 16777216 | 4096, 4096, 1, 1 | F16 | blk.13.attn_q.weight
60: 64 | 64, 1, 1, 1 | F32 | blk.13.attn_rot_embd
61: 4194304 | 4096, 1024, 1, 1 | F16 | blk.13.attn_v.weight
62: 4096 | 4096, 1, 1, 1 | F32 | blk.14.attn_norm.weight
63: 58720256 | 14336, 4096, 1, 1 | F16 | blk.14.ffn_down.weight
64: 58720256 | 4096, 14336, 1, 1 | F16 | blk.14.ffn_gate.weight
65: 58720256 | 4096, 14336, 1, 1 | F16 | blk.14.ffn_up.weight
66: 4096 | 4096, 1, 1, 1 | F32 | blk.14.ffn_norm.weight
67: 4194304 | 4096, 1024, 1, 1 | F16 | blk.14.attn_k.weight
68: 16777216 | 4096, 4096, 1, 1 | F16 | blk.14.attn_output.weight
69: 16777216 | 4096, 4096, 1, 1 | F16 | blk.14.attn_q.weight
70: 64 | 64, 1, 1, 1 | F32 | blk.14.attn_rot_embd
71: 4194304 | 4096, 1024, 1, 1 | F16 | blk.14.attn_v.weight
72: 4096 | 4096, 1, 1, 1 | F32 | blk.15.attn_norm.weight
73: 58720256 | 14336, 4096, 1, 1 | F16 | blk.15.ffn_down.weight
74: 58720256 | 4096, 14336, 1, 1 | F16 | blk.15.ffn_gate.weight
75: 58720256 | 4096, 14336, 1, 1 | F16 | blk.15.ffn_up.weight
76: 4096 | 4096, 1, 1, 1 | F32 | blk.15.ffn_norm.weight
77: 4194304 | 4096, 1024, 1, 1 | F16 | blk.15.attn_k.weight
78: 16777216 | 4096, 4096, 1, 1 | F16 | blk.15.attn_output.weight
79: 16777216 | 4096, 4096, 1, 1 | F16 | blk.15.attn_q.weight
80: 64 | 64, 1, 1, 1 | F32 | blk.15.attn_rot_embd
81: 4194304 | 4096, 1024, 1, 1 | F16 | blk.15.attn_v.weight
82: 4096 | 4096, 1, 1, 1 | F32 | blk.16.attn_norm.weight
83: 58720256 | 14336, 4096, 1, 1 | F16 | blk.16.ffn_down.weight
84: 58720256 | 4096, 14336, 1, 1 | F16 | blk.16.ffn_gate.weight
85: 58720256 | 4096, 14336, 1, 1 | F16 | blk.16.ffn_up.weight
86: 4096 | 4096, 1, 1, 1 | F32 | blk.16.ffn_norm.weight
87: 4194304 | 4096, 1024, 1, 1 | F16 | blk.16.attn_k.weight
88: 16777216 | 4096, 4096, 1, 1 | F16 | blk.16.attn_output.weight
89: 16777216 | 4096, 4096, 1, 1 | F16 | blk.16.attn_q.weight
90: 64 | 64, 1, 1, 1 | F32 | blk.16.attn_rot_embd
91: 4194304 | 4096, 1024, 1, 1 | F16 | blk.16.attn_v.weight
92: 4096 | 4096, 1, 1, 1 | F32 | blk.17.attn_norm.weight
93: 58720256 | 14336, 4096, 1, 1 | F16 | blk.17.ffn_down.weight
94: 58720256 | 4096, 14336, 1, 1 | F16 | blk.17.ffn_gate.weight
95: 58720256 | 4096, 14336, 1, 1 | F16 | blk.17.ffn_up.weight
96: 4096 | 4096, 1, 1, 1 | F32 | blk.17.ffn_norm.weight
97: 4194304 | 4096, 1024, 1, 1 | F16 | blk.17.attn_k.weight
98: 16777216 | 4096, 4096, 1, 1 | F16 | blk.17.attn_output.weight
99: 16777216 | 4096, 4096, 1, 1 | F16 | blk.17.attn_q.weight
100: 64 | 64, 1, 1, 1 | F32 | blk.17.attn_rot_embd
101: 4194304 | 4096, 1024, 1, 1 | F16 | blk.17.attn_v.weight
102: 4096 | 4096, 1, 1, 1 | F32 | blk.18.attn_norm.weight
103: 58720256 | 14336, 4096, 1, 1 | F16 | blk.18.ffn_down.weight
104: 58720256 | 4096, 14336, 1, 1 | F16 | blk.18.ffn_gate.weight
105: 58720256 | 4096, 14336, 1, 1 | F16 | blk.18.ffn_up.weight
106: 4096 | 4096, 1, 1, 1 | F32 | blk.18.ffn_norm.weight
107: 4194304 | 4096, 1024, 1, 1 | F16 | blk.18.attn_k.weight
108: 16777216 | 4096, 4096, 1, 1 | F16 | blk.18.attn_output.weight
109: 16777216 | 4096, 4096, 1, 1 | F16 | blk.18.attn_q.weight
110: 64 | 64, 1, 1, 1 | F32 | blk.18.attn_rot_embd
111: 4194304 | 4096, 1024, 1, 1 | F16 | blk.18.attn_v.weight
112: 4096 | 4096, 1, 1, 1 | F32 | blk.19.attn_norm.weight
113: 58720256 | 14336, 4096, 1, 1 | F16 | blk.19.ffn_down.weight
114: 58720256 | 4096, 14336, 1, 1 | F16 | blk.19.ffn_gate.weight
115: 58720256 | 4096, 14336, 1, 1 | F16 | blk.19.ffn_up.weight
116: 4096 | 4096, 1, 1, 1 | F32 | blk.19.ffn_norm.weight
117: 4194304 | 4096, 1024, 1, 1 | F16 | blk.19.attn_k.weight
118: 16777216 | 4096, 4096, 1, 1 | F16 | blk.19.attn_output.weight
119: 16777216 | 4096, 4096, 1, 1 | F16 | blk.19.attn_q.weight
120: 64 | 64, 1, 1, 1 | F32 | blk.19.attn_rot_embd
121: 4194304 | 4096, 1024, 1, 1 | F16 | blk.19.attn_v.weight
122: 4096 | 4096, 1, 1, 1 | F32 | blk.2.attn_norm.weight
123: 58720256 | 14336, 4096, 1, 1 | F16 | blk.2.ffn_down.weight
124: 58720256 | 4096, 14336, 1, 1 | F16 | blk.2.ffn_gate.weight
125: 58720256 | 4096, 14336, 1, 1 | F16 | blk.2.ffn_up.weight
126: 4096 | 4096, 1, 1, 1 | F32 | blk.2.ffn_norm.weight
127: 4194304 | 4096, 1024, 1, 1 | F16 | blk.2.attn_k.weight
128: 16777216 | 4096, 4096, 1, 1 | F16 | blk.2.attn_output.weight
129: 16777216 | 4096, 4096, 1, 1 | F16 | blk.2.attn_q.weight
130: 64 | 64, 1, 1, 1 | F32 | blk.2.attn_rot_embd
131: 4194304 | 4096, 1024, 1, 1 | F16 | blk.2.attn_v.weight
132: 4096 | 4096, 1, 1, 1 | F32 | blk.20.attn_norm.weight
133: 58720256 | 4096, 14336, 1, 1 | F16 | blk.20.ffn_gate.weight
134: 4096 | 4096, 1, 1, 1 | F32 | blk.20.ffn_norm.weight
135: 4194304 | 4096, 1024, 1, 1 | F16 | blk.20.attn_k.weight
136: 16777216 | 4096, 4096, 1, 1 | F16 | blk.20.attn_output.weight
137: 16777216 | 4096, 4096, 1, 1 | F16 | blk.20.attn_q.weight
138: 64 | 64, 1, 1, 1 | F32 | blk.20.attn_rot_embd
139: 4194304 | 4096, 1024, 1, 1 | F16 | blk.20.attn_v.weight
140: 4096 | 4096, 1, 1, 1 | F32 | blk.3.attn_norm.weight
141: 58720256 | 14336, 4096, 1, 1 | F16 | blk.3.ffn_down.weight
142: 58720256 | 4096, 14336, 1, 1 | F16 | blk.3.ffn_gate.weight
143: 58720256 | 4096, 14336, 1, 1 | F16 | blk.3.ffn_up.weight
144: 4096 | 4096, 1, 1, 1 | F32 | blk.3.ffn_norm.weight
145: 4194304 | 4096, 1024, 1, 1 | F16 | blk.3.attn_k.weight
146: 16777216 | 4096, 4096, 1, 1 | F16 | blk.3.attn_output.weight
147: 16777216 | 4096, 4096, 1, 1 | F16 | blk.3.attn_q.weight
148: 64 | 64, 1, 1, 1 | F32 | blk.3.attn_rot_embd
149: 4194304 | 4096, 1024, 1, 1 | F16 | blk.3.attn_v.weight
150: 4096 | 4096, 1, 1, 1 | F32 | blk.4.attn_norm.weight
151: 58720256 | 14336, 4096, 1, 1 | F16 | blk.4.ffn_down.weight
152: 58720256 | 4096, 14336, 1, 1 | F16 | blk.4.ffn_gate.weight
153: 58720256 | 4096, 14336, 1, 1 | F16 | blk.4.ffn_up.weight
154: 4096 | 4096, 1, 1, 1 | F32 | blk.4.ffn_norm.weight
155: 4194304 | 4096, 1024, 1, 1 | F16 | blk.4.attn_k.weight
156: 16777216 | 4096, 4096, 1, 1 | F16 | blk.4.attn_output.weight
157: 16777216 | 4096, 4096, 1, 1 | F16 | blk.4.attn_q.weight
158: 64 | 64, 1, 1, 1 | F32 | blk.4.attn_rot_embd
159: 4194304 | 4096, 1024, 1, 1 | F16 | blk.4.attn_v.weight
160: 4096 | 4096, 1, 1, 1 | F32 | blk.5.attn_norm.weight
161: 58720256 | 14336, 4096, 1, 1 | F16 | blk.5.ffn_down.weight
162: 58720256 | 4096, 14336, 1, 1 | F16 | blk.5.ffn_gate.weight
163: 58720256 | 4096, 14336, 1, 1 | F16 | blk.5.ffn_up.weight
164: 4096 | 4096, 1, 1, 1 | F32 | blk.5.ffn_norm.weight
165: 4194304 | 4096, 1024, 1, 1 | F16 | blk.5.attn_k.weight
166: 16777216 | 4096, 4096, 1, 1 | F16 | blk.5.attn_output.weight
167: 16777216 | 4096, 4096, 1, 1 | F16 | blk.5.attn_q.weight
168: 64 | 64, 1, 1, 1 | F32 | blk.5.attn_rot_embd
169: 4194304 | 4096, 1024, 1, 1 | F16 | blk.5.attn_v.weight
170: 4096 | 4096, 1, 1, 1 | F32 | blk.6.attn_norm.weight
171: 58720256 | 14336, 4096, 1, 1 | F16 | blk.6.ffn_down.weight
172: 58720256 | 4096, 14336, 1, 1 | F16 | blk.6.ffn_gate.weight
173: 58720256 | 4096, 14336, 1, 1 | F16 | blk.6.ffn_up.weight
174: 4096 | 4096, 1, 1, 1 | F32 | blk.6.ffn_norm.weight
175: 4194304 | 4096, 1024, 1, 1 | F16 | blk.6.attn_k.weight
176: 16777216 | 4096, 4096, 1, 1 | F16 | blk.6.attn_output.weight
177: 16777216 | 4096, 4096, 1, 1 | F16 | blk.6.attn_q.weight
178: 64 | 64, 1, 1, 1 | F32 | blk.6.attn_rot_embd
179: 4194304 | 4096, 1024, 1, 1 | F16 | blk.6.attn_v.weight
180: 4096 | 4096, 1, 1, 1 | F32 | blk.7.attn_norm.weight
181: 58720256 | 14336, 4096, 1, 1 | F16 | blk.7.ffn_down.weight
182: 58720256 | 4096, 14336, 1, 1 | F16 | blk.7.ffn_gate.weight
183: 58720256 | 4096, 14336, 1, 1 | F16 | blk.7.ffn_up.weight
184: 4096 | 4096, 1, 1, 1 | F32 | blk.7.ffn_norm.weight
185: 4194304 | 4096, 1024, 1, 1 | F16 | blk.7.attn_k.weight
186: 16777216 | 4096, 4096, 1, 1 | F16 | blk.7.attn_output.weight
187: 16777216 | 4096, 4096, 1, 1 | F16 | blk.7.attn_q.weight
188: 64 | 64, 1, 1, 1 | F32 | blk.7.attn_rot_embd
189: 4194304 | 4096, 1024, 1, 1 | F16 | blk.7.attn_v.weight
190: 4096 | 4096, 1, 1, 1 | F32 | blk.8.attn_norm.weight
191: 58720256 | 14336, 4096, 1, 1 | F16 | blk.8.ffn_down.weight
192: 58720256 | 4096, 14336, 1, 1 | F16 | blk.8.ffn_gate.weight
193: 58720256 | 4096, 14336, 1, 1 | F16 | blk.8.ffn_up.weight
194: 4096 | 4096, 1, 1, 1 | F32 | blk.8.ffn_norm.weight
195: 4194304 | 4096, 1024, 1, 1 | F16 | blk.8.attn_k.weight
196: 16777216 | 4096, 4096, 1, 1 | F16 | blk.8.attn_output.weight
197: 16777216 | 4096, 4096, 1, 1 | F16 | blk.8.attn_q.weight
198: 64 | 64, 1, 1, 1 | F32 | blk.8.attn_rot_embd
199: 4194304 | 4096, 1024, 1, 1 | F16 | blk.8.attn_v.weight
200: 4096 | 4096, 1, 1, 1 | F32 | blk.9.attn_norm.weight
201: 58720256 | 14336, 4096, 1, 1 | F16 | blk.9.ffn_down.weight
202: 58720256 | 4096, 14336, 1, 1 | F16 | blk.9.ffn_gate.weight
203: 58720256 | 4096, 14336, 1, 1 | F16 | blk.9.ffn_up.weight
204: 4096 | 4096, 1, 1, 1 | F32 | blk.9.ffn_norm.weight
205: 4194304 | 4096, 1024, 1, 1 | F16 | blk.9.attn_k.weight
206: 16777216 | 4096, 4096, 1, 1 | F16 | blk.9.attn_output.weight
207: 16777216 | 4096, 4096, 1, 1 | F16 | blk.9.attn_q.weight
208: 64 | 64, 1, 1, 1 | F32 | blk.9.attn_rot_embd
209: 4194304 | 4096, 1024, 1, 1 | F16 | blk.9.attn_v.weight
210: 525336576 | 4096, 128256, 1, 1 | F16 | output.weight
211: 58720256 | 14336, 4096, 1, 1 | F16 | blk.20.ffn_down.weight
212: 58720256 | 4096, 14336, 1, 1 | F16 | blk.20.ffn_up.weight
213: 4096 | 4096, 1, 1, 1 | F32 | blk.21.attn_norm.weight
214: 58720256 | 14336, 4096, 1, 1 | F16 | blk.21.ffn_down.weight
215: 58720256 | 4096, 14336, 1, 1 | F16 | blk.21.ffn_gate.weight
216: 58720256 | 4096, 14336, 1, 1 | F16 | blk.21.ffn_up.weight
217: 4096 | 4096, 1, 1, 1 | F32 | blk.21.ffn_norm.weight
218: 4194304 | 4096, 1024, 1, 1 | F16 | blk.21.attn_k.weight
219: 16777216 | 4096, 4096, 1, 1 | F16 | blk.21.attn_output.weight
220: 16777216 | 4096, 4096, 1, 1 | F16 | blk.21.attn_q.weight
221: 64 | 64, 1, 1, 1 | F32 | blk.21.attn_rot_embd
222: 4194304 | 4096, 1024, 1, 1 | F16 | blk.21.attn_v.weight
223: 4096 | 4096, 1, 1, 1 | F32 | blk.22.attn_norm.weight
224: 58720256 | 14336, 4096, 1, 1 | F16 | blk.22.ffn_down.weight
225: 58720256 | 4096, 14336, 1, 1 | F16 | blk.22.ffn_gate.weight
226: 58720256 | 4096, 14336, 1, 1 | F16 | blk.22.ffn_up.weight
227: 4096 | 4096, 1, 1, 1 | F32 | blk.22.ffn_norm.weight
228: 4194304 | 4096, 1024, 1, 1 | F16 | blk.22.attn_k.weight
229: 16777216 | 4096, 4096, 1, 1 | F16 | blk.22.attn_output.weight
230: 16777216 | 4096, 4096, 1, 1 | F16 | blk.22.attn_q.weight
231: 64 | 64, 1, 1, 1 | F32 | blk.22.attn_rot_embd
232: 4194304 | 4096, 1024, 1, 1 | F16 | blk.22.attn_v.weight
233: 4096 | 4096, 1, 1, 1 | F32 | blk.23.attn_norm.weight
234: 58720256 | 14336, 4096, 1, 1 | F16 | blk.23.ffn_down.weight
235: 58720256 | 4096, 14336, 1, 1 | F16 | blk.23.ffn_gate.weight
236: 58720256 | 4096, 14336, 1, 1 | F16 | blk.23.ffn_up.weight
237: 4096 | 4096, 1, 1, 1 | F32 | blk.23.ffn_norm.weight
238: 4194304 | 4096, 1024, 1, 1 | F16 | blk.23.attn_k.weight
239: 16777216 | 4096, 4096, 1, 1 | F16 | blk.23.attn_output.weight
240: 16777216 | 4096, 4096, 1, 1 | F16 | blk.23.attn_q.weight
241: 64 | 64, 1, 1, 1 | F32 | blk.23.attn_rot_embd
242: 4194304 | 4096, 1024, 1, 1 | F16 | blk.23.attn_v.weight
243: 4096 | 4096, 1, 1, 1 | F32 | blk.24.attn_norm.weight
244: 58720256 | 14336, 4096, 1, 1 | F16 | blk.24.ffn_down.weight
245: 58720256 | 4096, 14336, 1, 1 | F16 | blk.24.ffn_gate.weight
246: 58720256 | 4096, 14336, 1, 1 | F16 | blk.24.ffn_up.weight
247: 4096 | 4096, 1, 1, 1 | F32 | blk.24.ffn_norm.weight
248: 4194304 | 4096, 1024, 1, 1 | F16 | blk.24.attn_k.weight
249: 16777216 | 4096, 4096, 1, 1 | F16 | blk.24.attn_output.weight
250: 16777216 | 4096, 4096, 1, 1 | F16 | blk.24.attn_q.weight
251: 64 | 64, 1, 1, 1 | F32 | blk.24.attn_rot_embd
252: 4194304 | 4096, 1024, 1, 1 | F16 | blk.24.attn_v.weight
253: 4096 | 4096, 1, 1, 1 | F32 | blk.25.attn_norm.weight
254: 58720256 | 14336, 4096, 1, 1 | F16 | blk.25.ffn_down.weight
255: 58720256 | 4096, 14336, 1, 1 | F16 | blk.25.ffn_gate.weight
256: 58720256 | 4096, 14336, 1, 1 | F16 | blk.25.ffn_up.weight
257: 4096 | 4096, 1, 1, 1 | F32 | blk.25.ffn_norm.weight
258: 4194304 | 4096, 1024, 1, 1 | F16 | blk.25.attn_k.weight
259: 16777216 | 4096, 4096, 1, 1 | F16 | blk.25.attn_output.weight
260: 16777216 | 4096, 4096, 1, 1 | F16 | blk.25.attn_q.weight
261: 64 | 64, 1, 1, 1 | F32 | blk.25.attn_rot_embd
262: 4194304 | 4096, 1024, 1, 1 | F16 | blk.25.attn_v.weight
263: 4096 | 4096, 1, 1, 1 | F32 | blk.26.attn_norm.weight
264: 58720256 | 14336, 4096, 1, 1 | F16 | blk.26.ffn_down.weight
265: 58720256 | 4096, 14336, 1, 1 | F16 | blk.26.ffn_gate.weight
266: 58720256 | 4096, 14336, 1, 1 | F16 | blk.26.ffn_up.weight
267: 4096 | 4096, 1, 1, 1 | F32 | blk.26.ffn_norm.weight
268: 4194304 | 4096, 1024, 1, 1 | F16 | blk.26.attn_k.weight
269: 16777216 | 4096, 4096, 1, 1 | F16 | blk.26.attn_output.weight
270: 16777216 | 4096, 4096, 1, 1 | F16 | blk.26.attn_q.weight
271: 64 | 64, 1, 1, 1 | F32 | blk.26.attn_rot_embd
272: 4194304 | 4096, 1024, 1, 1 | F16 | blk.26.attn_v.weight
273: 4096 | 4096, 1, 1, 1 | F32 | blk.27.attn_norm.weight
274: 58720256 | 14336, 4096, 1, 1 | F16 | blk.27.ffn_down.weight
275: 58720256 | 4096, 14336, 1, 1 | F16 | blk.27.ffn_gate.weight
276: 58720256 | 4096, 14336, 1, 1 | F16 | blk.27.ffn_up.weight
277: 4096 | 4096, 1, 1, 1 | F32 | blk.27.ffn_norm.weight
278: 4194304 | 4096, 1024, 1, 1 | F16 | blk.27.attn_k.weight
279: 16777216 | 4096, 4096, 1, 1 | F16 | blk.27.attn_output.weight
280: 16777216 | 4096, 4096, 1, 1 | F16 | blk.27.attn_q.weight
281: 64 | 64, 1, 1, 1 | F32 | blk.27.attn_rot_embd
282: 4194304 | 4096, 1024, 1, 1 | F16 | blk.27.attn_v.weight
283: 4096 | 4096, 1, 1, 1 | F32 | blk.28.attn_norm.weight
284: 58720256 | 14336, 4096, 1, 1 | F16 | blk.28.ffn_down.weight
285: 58720256 | 4096, 14336, 1, 1 | F16 | blk.28.ffn_gate.weight
286: 58720256 | 4096, 14336, 1, 1 | F16 | blk.28.ffn_up.weight
287: 4096 | 4096, 1, 1, 1 | F32 | blk.28.ffn_norm.weight
288: 4194304 | 4096, 1024, 1, 1 | F16 | blk.28.attn_k.weight
289: 16777216 | 4096, 4096, 1, 1 | F16 | blk.28.attn_output.weight
290: 16777216 | 4096, 4096, 1, 1 | F16 | blk.28.attn_q.weight
291: 64 | 64, 1, 1, 1 | F32 | blk.28.attn_rot_embd
292: 4194304 | 4096, 1024, 1, 1 | F16 | blk.28.attn_v.weight
293: 4096 | 4096, 1, 1, 1 | F32 | blk.29.attn_norm.weight
294: 58720256 | 14336, 4096, 1, 1 | F16 | blk.29.ffn_down.weight
295: 58720256 | 4096, 14336, 1, 1 | F16 | blk.29.ffn_gate.weight
296: 58720256 | 4096, 14336, 1, 1 | F16 | blk.29.ffn_up.weight
297: 4096 | 4096, 1, 1, 1 | F32 | blk.29.ffn_norm.weight
298: 4194304 | 4096, 1024, 1, 1 | F16 | blk.29.attn_k.weight
299: 16777216 | 4096, 4096, 1, 1 | F16 | blk.29.attn_output.weight
300: 16777216 | 4096, 4096, 1, 1 | F16 | blk.29.attn_q.weight
301: 64 | 64, 1, 1, 1 | F32 | blk.29.attn_rot_embd
302: 4194304 | 4096, 1024, 1, 1 | F16 | blk.29.attn_v.weight
303: 4096 | 4096, 1, 1, 1 | F32 | blk.30.attn_norm.weight
304: 58720256 | 14336, 4096, 1, 1 | F16 | blk.30.ffn_down.weight
305: 58720256 | 4096, 14336, 1, 1 | F16 | blk.30.ffn_gate.weight
306: 58720256 | 4096, 14336, 1, 1 | F16 | blk.30.ffn_up.weight
307: 4096 | 4096, 1, 1, 1 | F32 | blk.30.ffn_norm.weight
308: 4194304 | 4096, 1024, 1, 1 | F16 | blk.30.attn_k.weight
309: 16777216 | 4096, 4096, 1, 1 | F16 | blk.30.attn_output.weight
310: 16777216 | 4096, 4096, 1, 1 | F16 | blk.30.attn_q.weight
311: 64 | 64, 1, 1, 1 | F32 | blk.30.attn_rot_embd
312: 4194304 | 4096, 1024, 1, 1 | F16 | blk.30.attn_v.weight
313: 4096 | 4096, 1, 1, 1 | F32 | blk.31.attn_norm.weight
314: 58720256 | 14336, 4096, 1, 1 | F16 | blk.31.ffn_down.weight
315: 58720256 | 4096, 14336, 1, 1 | F16 | blk.31.ffn_gate.weight
316: 58720256 | 4096, 14336, 1, 1 | F16 | blk.31.ffn_up.weight
317: 4096 | 4096, 1, 1, 1 | F32 | blk.31.ffn_norm.weight
318: 4194304 | 4096, 1024, 1, 1 | F16 | blk.31.attn_k.weight
319: 16777216 | 4096, 4096, 1, 1 | F16 | blk.31.attn_output.weight
320: 16777216 | 4096, 4096, 1, 1 | F16 | blk.31.attn_q.weight
321: 64 | 64, 1, 1, 1 | F32 | blk.31.attn_rot_embd
322: 4194304 | 4096, 1024, 1, 1 | F16 | blk.31.attn_v.weight
323: 4096 | 4096, 1, 1, 1 | F32 | output_norm.weight